1 / 60

Image Categorization

03/15/11. Image Categorization. Computer Vision CS 543 / ECE 549 University of Illinois Derek Hoiem. Thanks for feedback HW 3 is out Project guidelines are out. Last classes. Object recognition: localizing an object instance in an image

yakov
Download Presentation

Image Categorization

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. 03/15/11 Image Categorization Computer Vision CS 543 / ECE 549 University of Illinois Derek Hoiem

  2. Thanks for feedback • HW 3 is out • Project guidelines are out

  3. Last classes • Object recognition: localizing an object instance in an image • Face recognition: matching one face image to another

  4. Today’s class: categorization • Overview of image categorization • Representation • Image histograms • Classification • Important concepts in machine learning • What the classifiers are and when to use them

  5. What is a category? • Why would we want to put an image in one? • Many different ways to categorize To predict, describe, interact. To organize.

  6. Image Categorization Training Training Labels Training Images Image Features Classifier Training Trained Classifier

  7. Image Categorization Training Training Labels Training Images Image Features Classifier Training Trained Classifier Testing Prediction Image Features Trained Classifier Outdoor Test Image

  8. Part 1: Image features Training Training Labels Training Images Image Features Classifier Training Trained Classifier

  9. General Principles of Representation • Coverage • Ensure that all relevant info is captured • Concision • Minimize number of features without sacrificing coverage • Directness • Ideal features are independently useful for prediction Image Intensity

  10. Image representations • Templates • Intensity, gradients, etc. • Histograms • Color, texture, SIFT descriptors, etc.

  11. Image Representations: Histograms Global histogram • Represent distribution of features • Color, texture, depth, … Space Shuttle Cargo Bay Images from Dave Kauchak

  12. Image Representations: Histograms Histogram: Probability or count of data in each bin • Joint histogram • Requires lots of data • Loss of resolution to avoid empty bins • Marginal histogram • Requires independent features • More data/bin than joint histogram Images from Dave Kauchak

  13. Image Representations: Histograms Clustering EASE Truss Assembly Use the same cluster centers for all images Space Shuttle Cargo Bay Images from Dave Kauchak

  14. Computing histogram distance Histogram intersection (assuming normalized histograms) Chi-squared Histogram matching distance Cars found by color histogram matching using chi-squared

  15. Histograms: Implementation issues • Quantization • Grids: fast but applicable only with few dimensions • Clustering: slower but can quantize data in higher dimensions • Matching • Histogram intersection or Euclidean may be faster • Chi-squared often works better • Earth mover’s distance is good for when nearby bins represent similar values Few Bins Need less data Coarser representation Many Bins Need more data Finer representation

  16. What kind of things do we compute histograms of? • Color • Texture (filter banks or HOG over regions) L*a*b* color space HSV color space

  17. What kind of things do we compute histograms of? • Histograms of oriented gradients • “Bag of words” SIFT – Lowe IJCV 2004

  18. Image Categorization: Bag of Words Training • Extract keypoints and descriptors for all training images • Cluster descriptors • Quantize descriptors using cluster centers to get “visual words” • Represent each image by normalized counts of “visual words” • Train classifier on labeled examples using histogram values as features Testing • Extract keypoints/descriptors and quantize into visual words • Compute visual word histogram • Compute label or confidence using classifier

  19. But what about layout? All of these images have the same color histogram

  20. Spatial pyramid Compute histogram in each spatial bin

  21. Right features depend on what you want to know • Shape: scene-scale, object-scale, detail-scale • 2D form, shading, shadows, texture, linear perspective • Material properties: albedo, feel, hardness, … • Color, texture • Motion • Optical flow, tracked points • Distance • Stereo, position, occlusion, scene shape • If known object: size, other objects

  22. Things to remember about representation • Most features can be thought of as templates, histograms (counts), or combinations • Think about the right features for the problem • Coverage • Concision • Directness

  23. Part 2: Classifiers Training Training Labels Training Images Image Features Classifier Training Trained Classifier

  24. Learning a classifier Given some set of features with corresponding labels, learn a function to predict the labels from the features x x x x x x x o x o o o o x2 x1

  25. One way to think about it… • Training labels dictate that two examples are the same or different, in some sense • Features and distance measures define visual similarity • Classifiers try to learn weights or parameters for features and distance measures so that visual similarity predicts label similarity

  26. Many classifiers to choose from • SVM • Neural networks • Naïve Bayes • Bayesian network • Logistic regression • Randomized Forests • Boosted Decision Trees • K-nearest neighbor • RBMs • Etc. Which is the best one?

  27. No Free Lunch Theorem

  28. Bias-Variance Trade-off E(MSE) = noise2 + bias2 + variance Error due to variance of training samples Unavoidable error Error due to incorrect assumptions • See the following for explanations of bias-variance (also Bishop’s “Neural Networks” book): • http://www.stat.cmu.edu/~larry/=stat707/notes3.pdf • http://www.inf.ed.ac.uk/teaching/courses/mlsc/Notes/Lecture4/BiasVariance.pdf

  29. Bias and Variance Error = noise2 + bias2 + variance Few training examples Test Error Many training examples High Bias Low Variance Complexity Low Bias High Variance

  30. Choosing the trade-off • Need validation set • Validation set not same as test set Test error Error Training error High Bias Low Variance Complexity Low Bias High Variance

  31. Effect of Training Size Fixed classifier Error Testing Generalization Error Training Number of Training Examples

  32. How to measure complexity? • VC dimension • Other ways: number of parameters, etc. What is the VC dimension of a linear classifier for N-dimensional features? For a nearest neighbor classifier? Upper bound on generalization error Training error + N: size of training set h: VC dimension : 1-probability that bound holds

  33. How to reduce variance? • Choose a simpler classifier • Regularize the parameters • Get more training data Which of these could actually lead to greater error?

  34. Reducing Risk of Error • Margins x x x x x x x o x o o o o x2 x1

  35. The perfect classification algorithm • Objective function: encodes the right loss for the problem • Parameterization: makes assumptions that fit the problem • Regularization: right level of regularization for amount of training data • Training algorithm: can find parameters that maximize objective on training set • Inference algorithm: can solve for objective function in evaluation

  36. Generative vs. Discriminative Classifiers Generative • Training • Models the data and the labels • Assume (or learn) probability distribution and dependency structure • Can impose priors • Testing • P(y=1, x) / P(y=0, x) > t? • Examples • Foreground/background GMM • Naïve Bayes classifier • Bayesian network Discriminative • Training • Learn to directly predict the labels from the data • Assume form of boundary • Margin maximization or parameter regularization • Testing • f(x) > t ; e.g., wTx > t • Examples • Logistic regression • SVM • Boosted decision trees

  37. K-nearest neighbor + x x + o x x x x o x o x o o o o x2 x1

  38. 1-nearest neighbor + x x + o x x x x o x o x o o o o x2 x1

  39. 3-nearest neighbor + x x + o x x x x o x o x o o o o x2 x1

  40. 5-nearest neighbor + x x + o x x x x o x o x o o o What is the parameterization? The regularization? The training algorithm? The inference? o x2 x1 Is K-NN generative or discriminative?

  41. Using K-NN • Simple, a good one to try first • With infinite examples, 1-NN provably has error that is at most twice Bayes optimal error

  42. Naïve Bayes • Objective • Parameterization • Regularization • Training • Inference y x1 x2 x3

  43. Using Naïve Bayes • Simple thing to try for categorical data • Very fast to train/test

  44. Classifiers: Logistic Regression • Objective • Parameterization • Regularization • Training • Inference x x x x x x x o x o o o o x2 x1

  45. Using Logistic Regression • Quick, simple classifier (try it first) • Use L2 or L1 regularization • L1 does feature selection and is robust to irrelevant features but slower to train

  46. Classifiers: Linear SVM x x x x x x x o x o o o o x2 x1

  47. Classifiers: Linear SVM x x x x x x x o x o o o o x2 x1

  48. Classifiers: Linear SVM • Objective • Parameterization • Regularization • Training • Inference x x o x x x x x o x o o o o x2 x1

  49. Classifiers: Kernelized SVM x x o o o x x x x x o o x2 o x x x

  50. Using SVMs • Good general purpose classifier • Generalization depends on margin, so works well with many weak features • No feature selection • Usually requires some parameter tuning • Choosing kernel • Linear: fast training/testing – start here • RBF: related to neural networks, nearest neighbor • Chi-squared, histogram intersection: good for histograms (but slower, esp. chi-squared) • Can learn a kernel function

More Related